George Oliveira Barros

George Oliveira Barros

Auto-generated profile, based on publicly available information

George Oliveira Barros

Instituto Federal Goiano, Brazil

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 September 2024 in IEEE Journal of Translational Engineering in Health and Medicine
Verified
Journal Article
Open access
GBGeorge Oliveira Barros
George Oliveira Barros
JSJosé Nathan Andrade Muller da Silva
José Nathan Andrade Muller da Silva
HPHenrique Machado de Sousa Proença
Henrique Machado de Sousa Proença
SAStanley Almeida Araújo
Stanley Almeida Araújo
DWDavid Campos Wanderley
David Campos Wanderley
FVFlavio Vidal
Flavio Vidal
Podocyte degenerative changes are common in various kidney diseases, and their accurate identification is crucial for pathologists to diagnose and treat such conditions. However, this can be a difficult task, and previous attempts to automate the identification of podocytes have not been entirely successful. To address this issue, this study proposes a novel approach that combines pathologists’ expertise with an automated classifier to enhance the identification of podocytopathies. The study involved building a new dataset of renal glomeruli images, some with and others without podocyte degenerative changes, and developing a convolutional neural network (CNN) based classifier. The results showed that our automated classifier achieved an impressive 90.9% f-score. When the pathologists used as an auxiliary tool to classify a second set of images, the medical group’s average performance increased significantly, from $91.4\pm 12.5$ % to $96.1\pm 2.9$ % of f-score. Fleiss’ kappa agreement among the pathologists also increased from 0.59 to 0.83. Conclusion: These findings suggest that automating this task can bring benefits for pathologists to correctly identify images of glomeruli with podocyte degeneration, leading to improved individual accuracy while raising agreement in diagnosing podocytopathies. This approach could have significant implications for the diagnosis and treatment of kidney diseases. Clinical impact: The approach presented in this study has the potential to enhance the accuracy of medical diagnoses for detecting podocyte abnormalities in glomeruli, which serve as biomarkers for various glomerular diseases.

31 May 2023 in Research Square
Verified
Preprint
Open access
PDF file
GBGeorge Oliveira Barros
George Oliveira Barros
JSJosé Nathan Andrade Muller da Silva
José Nathan Andrade Muller da Silva
HPHenrique Machado de Sousa Proença
Henrique Machado de Sousa Proença
SAStanley Almeida Araújo
Stanley Almeida Araújo
DWDavid Campos Wanderley
David Campos Wanderley
FVFlávio de Barros Vidal
Flávio de Barros Vidal
The authors have requested that this preprint be removed from Research Square.

16 March 2023 in Extensão Tecnológica: Revista de Extensão do Instituto Federal Catarinense
Verified
Journal Article
Open access
PDF file
ADAdriano Antonio Brito Darosci
Adriano Antonio Brito Darosci
GSGabriel Da Mata Santana
Gabriel Da Mata Santana
GBGeorge Oliveira Barros
George Oliveira Barros
TMThasia Martins Macedo
Thasia Martins Macedo
Ítalo José Bastos GuimarãesÍtalo José Bastos Guimarães
Ítalo José Bastos Guimarães
A pandemia da Covid-19 acomete a economia do país, uma vez que a comercialização de muitos produtos é reduzida sem a oferta e a procura tradicionais que dependem da população “nas ruas”. Contudo, o isolamento social é necessário para conter o vírus e novas estratégias para continuar mantendo a economia são urgentes. Dentre os personagens da economia mais afetados pelo cenário pandêmico estão os pequenos produtores e os extrativistas, uma vez que dependem principalmente do comércio boca a boca que costuma ser evitado nestas ocasiões. A fim de auxiliar a manutenção dessa atividade econômica, considerada mais sustentável, ferramentas que possibilitam a negociação entre o produtor e o consumidor podem ser uma estratégia eficiente. Desse modo, o objetivo do presente trabalho foi o desenvolvimento do site “Sustentar”, que reúne e divulga imagens e informações dos produtos ofertados pelos pequenos produtores e extrativistas, para estarem acessíveis por todos. Para tanto, levantou-se requisitos básicos junto ao público-alvo, a fim de criar protótipos, que foram testados antes de serem codificados por diferentes tecnologias. O site permite, ainda, o contato entre produtores/extrativistas e cooperativas disponíveis na região do Cerrado, a fim de poderem trabalhar de forma integrada, com a formação de grupos sob uma base cultural comum e obter vantagens fiscais e comunitárias, essenciais para a sobrevivência desse comércio. Uma vez já desenvolvida, espera-se que tal plataforma, armazenada em um servidor Web, possa passar por outras fases de testes e ser, então, divulgada e utilizada pelos setores-alvo e pelo público usuário da internet.

4 May 2026 in Journal of Food Measurement and Characterization
Verified
Journal Article
Open access
Lucas SantanaLucas Santana
Lucas Santana
JSJosiane Maria da Silva
Josiane Maria da Silva
Gabriel Araujo e Silva FerrazGabriel Araujo e Silva Ferraz
Gabriel Araujo e Silva Ferraz
MSMozarte Santos Santana
Mozarte Santos Santana
LSLucas Gabryel Maciel dos Santos
Lucas Gabryel Maciel dos Santos
GBGianluca Bambi
Gianluca Bambi
Coffee fruit drying is an essential step, as it directly affects the drink’s final quality. The presence of green fruits in this process significantly reduces the quality standard. Conventional characterization techniques are performed manually, are time-consuming, and lead to increased estimation errors. Thus, the objective was to identify green, red, and black fruits in the drying patio by digital classification of multispectral and RGB images. The data were obtained by remotely piloted aircraft during daily flights over coffee fruits for eight days of drying. The analyses involved color segregation techniques, supervised classification (Random Forest), and the application of thirty vegetation indices to RGB and multispectral images, utilizing Python, RStudio, and GIS to generate statistical models and maps, in conjunction with manual fruit estimation and monitoring of temperature and humidity. The use of aerial images proved effective in monitoring colors only during the first three days, due to rapid moisture loss. In all analyses, green fruits showed better spectral separation. Image segmentation proved to be the superior method, adequate up to the third day. Random Forest showed reduced performance due to shadows and color mixing and was only effective on the first day. Among the RGB indices, ExGR and MGRVI stood out, with high potential for detecting green fruits, while TGI indicated two classes of green, highlighting the efficiency of conventional sensors. For multispectral images, NDVI was effective on the first day, and NDWI was effective up to the third day, influenced by fruit of humidity reduction. The need to develop a specific vegetative index to standardize this monitoring is emphasized, based on green separation, considering humidity and robust quality indicators.